Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate gradual progress or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     üzerine
    -0.16
    arken
    -0.15
    enan
    -0.15
    OnInit
    -0.15
     Dalton
    -0.15
    ompiler
    -0.14
    ermann
    -0.14
    üç
    -0.14
    ª
    -0.14
    ÑĢалÑĮ
    -0.14
    POSITIVE LOGITS
     slowly
    0.25
    kowski
    0.20
     gradually
    0.19
    slow
    0.18
     Slow
    0.18
     gradual
    0.17
     dần
    0.17
    Slow
    0.17
     slow
    0.17
     increment
    0.16
    Act Density 0.055%

    No Known Activations